105 citations · 129 across the 29 of their papers we have counts for
8 papers · 1 filter
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
Yichen Feng, Yuetai Li, Chunjiang Liu +14
Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an expl…
3D4D: An Interactive, Editable, 4D World Model via 3D Video Generation
Yunhong He, Zhengqing Yuan, Zhengzhong Tu +2
We introduce 3D4D, an interactive 4D visualization framework that integrates WebGL with Supersplat rendering. It transforms static images and text into coherent 4D scenes through f…
Biomedical SAM 2: Segment Anything in Biomedical Images and Videos
Zhiling Yan, Weixiang Sun, Rong Zhou +8
Medical image segmentation and video object segmentation are essential for diagnosing and analyzing diseases by identifying and measuring biological structures. Recent advances in…
Bora: Biomedical Generalist Video Generation Model
Weixiang Sun, Xiaocao You, Ruizhe Zheng +5
Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for medical AI development. Diffusion models can now generate re…
ViT-1.58b: Mobile Vision Transformers in the 1-bit Era
Zhengqing Yuan, Rong Zhou, Hongyi Wang +3
Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens. Howe…
Mora: Enabling Generalist Video Generation via A Multi-Agent Framework
Zhengqing Yuan, Yixin Liu, Yihan Cao +10
Text-to-video generation has made significant strides, but replicating the capabilities of advanced systems like OpenAI Sora remains challenging due to their closed-source nature.…
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
Yixin Liu, Kai Zhang, Yuan Li +9
Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is trained to generate videos of realistic or imaginative scenes from text instructions…
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
Zhengqing Yuan, Zhaoxu Li, Weiran Huang +2
In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks. Despite their p…